© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43353
    Prev
    Next
    INDEX
    Explanations

    .sub and .sup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ؤ
    -0.07
    olor
    -0.07
    oub
    -0.07
    ез
    -0.07
    owing
    -0.06
    furt
    -0.06
    äºĨçĦ¶
    -0.06
    \\.
    -0.06
    äd
    -0.06
    .Builder
    -0.06
    POSITIVE LOGITS
     gesta
    0.08
    kert
    0.07
    klin
    0.07
    ä¸Ģä½ľ
    0.07
    oram
    0.07
    noi
    0.07
    åĴĮä¹īåĬ¡
    0.07
    ÛĮ
    0.07
    roj
    0.07
    നി
    0.07
    Activations Density 0.001%

    No Known Activations